01
The hard part isn't starting agents, it's tracking them
Opening a second Claude Code session takes one terminal tab. Knowing which of your six sessions finished, which one has been waiting on a permission for twenty minutes, and which one quietly stalled: that's the part that doesn't scale. AgentPeek puts every session in the Mac notch, labeled by project, with its state readable at a glance: executing, thinking, waiting, or idle, plus an attention flag when a session needs you. There's no session cap beyond what your Mac can run.
02
Launch the whole fleet in one click
Views open one terminal window split into panes, each running the agent CLI you chose (claude, codex, cursor-agent, and the rest) in the folder you chose. Save a View for your standing setup, launch it, and every session appears in AgentPeek seconds later. Mixing vendors is the point: run Claude Code on the app repo while Codex works the API repo and Cursor handles a refactor.
03
Answer whoever needs you, in order
When several agents want you at once, their permission prompts and questions stack in the notch; arrow keys move between them and a keystroke answers each one. The Agent Board keeps the wide view as a floating kanban: what's working, what needs attention, what's finished, sorted on its own while you work.
04
Per-agent usage while you scale up
Parallel work burns quota in parallel. AgentPeek shows live usage gauges per agent: 5-hour and 7-day windows for Claude Code and Codex, Cursor's monthly window, and token totals for the local-log agents, with a budget alert before a limit lands. The headline picks up to four agents to keep on the collapsed pill, so the numbers you're pacing against never leave your screen.